Classification of High‐Latitude Source Region‐Based Ionospheric Scintillation Signatures Using Machine Learning

AbstractThis study investigates ionospheric scintillation signatures in GNSS signals at high latitudes with Machine Learning (ML), focusing on different irregularity generation mechanisms in major regions of the ionosphere. The diverse structuring in various scale sizes resulting from these mechanisms might produce distinct scintillation signatures. In the nightside ionosphere, precipitation is predominantly observed in the auroral oval versus density gradients in the polar cap. We apply this physics‐based precursor knowledge about the source regions and establish a database of scintillation events from significant geomagnetic activity to explore these differences in scintillation signatures. Scintillation event segments in high‐rate (50 Hz) Global Navigation Satellite System (GNSS) signal phase and amplitude are selected as input data to analyze time‐dependent signature features. These pre‐processed events are collected from stations in the auroral oval and polar cap regions and labeled based on ionospheric conditions during four geomagnetic storms. Using this database, we train an ML model to classify events into polar cap versus auroral oval signatures in two systematic steps. I